Compare AI models

Specifications
Parameters
—4B/30B/235B
Context window
1M256k
API pricing
Cheapest input
$0.03Particle AI—
Cheapest output
$0.2352DeepInfra—
$25.00Pearl Research · fp8—
Benchmarks
Humanity's Last Exam · text only, no tools
44%18.2%
Overview
CompanyDeepSeekQwen
Release dateOct 17 2026Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-V4.1-Flash-1017 leads Qwen3-2507 on 1 of the 1 benchmark they both report (Humanity's Last Exam). Qwen3-2507 shipped 453 days before DeepSeek-V4.1-Flash-1017, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (DeepSeek-V4.1-Flash-1017) vs 256k (Qwen3-2507).

On Humanity's Last Exam · text only, no tools, DeepSeek-V4.1-Flash-1017 leads at 44% vs Qwen3-2507 at 18.2%.